StreamLake

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by StreamLake

Model name

30 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek R1-0528 deepseek-ai/DeepSeek-R1-0528:streamlake	128k	$0.60/M	$2.40/M	N/A	3.2s	44 tps
DeepSeek V3.1 Terminus deepseek-ai/DeepSeek-V3.1-Terminus:streamlake	128k	$0.36/M	$1.08/M	N/A	1s	46 tps
DeepSeek V3.1 Terminus (Thinking) deepseek-ai/DeepSeek-V3.1-Terminus:thinking:streamlake	128k	$0.36/M	$1.08/M	N/A	1s	46 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:streamlake	1.0M	$0.14/M	$0.42/M	$0.0044/M	1.4s	42 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:streamlake	1.0M	$0.14/M	$0.42/M	$0.0044/M	1.4s	42 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:streamlake	1.0M	$1.83/M	$3.65/M	$0.15/M	3.2s	31.5 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:streamlake	1.0M	$1.83/M	$3.65/M	$0.15/M	3.2s	31.5 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:streamlake	1.0M	$0.69/M	$2.08/M	$0.02/M	1.7s	43 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:streamlake	1.0M	$0.69/M	$2.08/M	$0.02/M	1.7s	43 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:streamlake	1.0M	$0.15/M	$0.62/M	$0.0031/M	1.3s	77 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:streamlake	1.0M	$0.15/M	$0.62/M	$0.0031/M	1.3s	77 tps
GLM 5 FP8 z-ai/glm-5:streamlake	198k	$0.63/M	$2.02/M	$0.13/M	2s	60 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:streamlake	198k	$0.63/M	$2.02/M	$0.13/M	2s	60 tps
GLM 5.1 FP8 z-ai/glm-5.1:streamlake	200k	$1.01/M	$3.19/M	$0.19/M	1.8s	51 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:streamlake	200k	$1.01/M	$3.19/M	$0.19/M	1.8s	51 tps
GLM 5.2 FP8 z-ai/glm-5.2:streamlake	1.0M	$0.64/M	$2.02/M	$0.12/M	1.2s	54 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:streamlake	1.0M	$0.64/M	$2.02/M	$0.12/M	1.2s	54 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:streamlake	1.0M	$0.05/M	$0.15/M	$0.0091/M	1.6s	34 tps
Kimi K2.6 FP8 moonshotai/kimi-k2.6:streamlake	256k	$0.63/M	$2.65/M	$0.11/M	2.5s	30 tps
Kimi K2.6 Thinking FP8 moonshotai/kimi-k2.6:thinking:streamlake	256k	$0.63/M	$2.65/M	$0.11/M	2.5s	30 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:streamlake	256k	$0.75/M	$3.15/M	$0.15/M	1.2s	60 tps
MiMo V2.5 xiaomi/mimo-v2.5:streamlake	1M	$0.18/M	$0.35/M	$0.0035/M	2.2s	18 tps
MiMo V2.5 Pro xiaomi/mimo-v2.5-pro:streamlake	1M	$0.55/M	$1.10/M	$0.0045/M	1.3s	23 tps
MiMo V2.5 Pro Thinking xiaomi/mimo-v2.5-pro:thinking:streamlake	1M	$0.55/M	$1.10/M	$0.0045/M	1.3s	23 tps
MiMo V2.5 Thinking xiaomi/mimo-v2.5:thinking:streamlake	1M	$0.18/M	$0.35/M	$0.0035/M	2.2s	18 tps
MiniMax M2.5 minimax/minimax-m2.5:streamlake	200k	$0.28/M	$1.13/M	$0.03/M	0.7s	113.5 tps
MiniMax M3 FP8 minimax/minimax-m3:streamlake	1M	$0.31/M	$1.26/M	$0.06/M	1.4s	95 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:streamlake	1M	$0.31/M	$1.26/M	$0.06/M	1.4s	95 tps
Qwen3.5 397B qwen/qwen3.5-397b-a17b:streamlake	256k	$0.63/M	$3.78/M	$0.13/M	0.6s	100 tps
Qwen3.5 397B Thinking qwen/qwen3.5-397b-a17b-thinking:streamlake	256k	$0.63/M	$3.78/M	$0.13/M	0.6s	100 tps

DeepSeek R1-0528

deepseek-ai/DeepSeek-R1-0528:streamlake

Context

128k

Input /M

$0.60/M

Output /M

$2.40/M

Cache read /M

N/A

TTFT

3.2s

Throughput

44 tps

DeepSeek V3.1 Terminus

deepseek-ai/DeepSeek-V3.1-Terminus:streamlake

Context

128k

Input /M

$0.36/M

Output /M

$1.08/M

Cache read /M

N/A

TTFT

1s

Throughput

46 tps

DeepSeek V3.1 Terminus (Thinking)

deepseek-ai/DeepSeek-V3.1-Terminus:thinking:streamlake

Context

128k

Input /M

$0.36/M

Output /M

$1.08/M

Cache read /M

N/A

TTFT

1s

Throughput

46 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:streamlake

Context

1.0M

Input /M

$0.14/M

Output /M

$0.42/M

Cache read /M

$0.0044/M

TTFT

1.4s

Throughput

42 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

deepseek/deepseek-v4-flash-0731:thinking:streamlake

Context

1.0M

Input /M

$0.14/M

Output /M

$0.42/M

Cache read /M

$0.0044/M

TTFT

1.4s

Throughput

42 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:streamlake

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

TTFT

3.2s

Throughput

31.5 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:streamlake

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

TTFT

3.2s

Throughput

31.5 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:streamlake

Context

1.0M

Input /M

$0.69/M

Output /M

$2.08/M

Cache read /M

$0.02/M

TTFT

1.7s

Throughput

43 tps

DeepSeek V4 Pro 0813 (Thinking)

deepseek/deepseek-v4-pro-0813:thinking:streamlake

Context

1.0M

Input /M

$0.69/M

Output /M

$2.08/M

Cache read /M

$0.02/M

TTFT

1.7s

Throughput

43 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:streamlake

Context

1.0M

Input /M

$0.15/M

Output /M

$0.62/M

Cache read /M

$0.0031/M

TTFT

1.3s

Throughput

77 tps

DeepSeek V4.1 Flash (Thinking)

FP8

deepseek/deepseek-v4.1-flash:thinking:streamlake

Context

1.0M

Input /M

$0.15/M

Output /M

$0.62/M

Cache read /M

$0.0031/M

TTFT

1.3s

Throughput

77 tps

GLM 5

FP8

z-ai/glm-5:streamlake

Context

198k

Input /M

$0.63/M

Output /M

$2.02/M

Cache read /M

$0.13/M

TTFT

2s

Throughput

60 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:streamlake

Context

198k

Input /M

$0.63/M

Output /M

$2.02/M

Cache read /M

$0.13/M

TTFT

2s

Throughput

60 tps

GLM 5.1

FP8

z-ai/glm-5.1:streamlake

Context

200k

Input /M

$1.01/M

Output /M

$3.19/M

Cache read /M

$0.19/M

TTFT

1.8s

Throughput

51 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:streamlake

Context

200k

Input /M

$1.01/M

Output /M

$3.19/M

Cache read /M

$0.19/M

TTFT

1.8s

Throughput

51 tps

GLM 5.2

FP8

z-ai/glm-5.2:streamlake

Context

1.0M

Input /M

$0.64/M

Output /M

$2.02/M

Cache read /M

$0.12/M

TTFT

1.2s

Throughput

54 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:streamlake

Context

1.0M

Input /M

$0.64/M

Output /M

$2.02/M

Cache read /M

$0.12/M

TTFT

1.2s

Throughput

54 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:streamlake

Context

1.0M

Input /M

$0.05/M

Output /M

$0.15/M

Cache read /M

$0.0091/M

TTFT

1.6s

Throughput

34 tps

Kimi K2.6

FP8

moonshotai/kimi-k2.6:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$2.65/M

Cache read /M

$0.11/M

TTFT

2.5s

Throughput

30 tps

Kimi K2.6 Thinking

FP8

moonshotai/kimi-k2.6:thinking:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$2.65/M

Cache read /M

$0.11/M

TTFT

2.5s

Throughput

30 tps

Kimi K2.7 Code

moonshotai/kimi-k2.7-code:streamlake

Context

256k

Input /M

$0.75/M

Output /M

$3.15/M

Cache read /M

$0.15/M

TTFT

1.2s

Throughput

60 tps

MiMo V2.5

xiaomi/mimo-v2.5:streamlake

Context

1M

Input /M

$0.18/M

Output /M

$0.35/M

Cache read /M

$0.0035/M

TTFT

2.2s

Throughput

18 tps

MiMo V2.5 Pro

xiaomi/mimo-v2.5-pro:streamlake

Context

1M

Input /M

$0.55/M

Output /M

$1.10/M

Cache read /M

$0.0045/M

TTFT

1.3s

Throughput

23 tps

MiMo V2.5 Pro Thinking

xiaomi/mimo-v2.5-pro:thinking:streamlake

Context

1M

Input /M

$0.55/M

Output /M

$1.10/M

Cache read /M

$0.0045/M

TTFT

1.3s

Throughput

23 tps

MiMo V2.5 Thinking

xiaomi/mimo-v2.5:thinking:streamlake

Context

1M

Input /M

$0.18/M

Output /M

$0.35/M

Cache read /M

$0.0035/M

TTFT

2.2s

Throughput

18 tps

MiniMax M2.5

minimax/minimax-m2.5:streamlake

Context

200k

Input /M

$0.28/M

Output /M

$1.13/M

Cache read /M

$0.03/M

TTFT

0.7s

Throughput

113.5 tps

MiniMax M3

FP8

minimax/minimax-m3:streamlake

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

1.4s

Throughput

95 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:streamlake

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

1.4s

Throughput

95 tps

Qwen3.5 397B

qwen/qwen3.5-397b-a17b:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.13/M

TTFT

0.6s

Throughput

100 tps

Qwen3.5 397B Thinking

qwen/qwen3.5-397b-a17b-thinking:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.13/M

TTFT

0.6s

Throughput

100 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using StreamLake via the API

Call a model served by StreamLake using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-0528:streamlake",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :streamlake to the model ID, set "provider": "streamlake" in the request body, or send an X-Provider: streamlake header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.